{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:06:57Z","timestamp":1764997617945,"version":"3.38.0"},"reference-count":19,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDT"],"published-print":{"date-parts":[[2024,9,16]]},"abstract":"<jats:p>Sentiment analysis, which involves determining the emotional polarity positivity, negativity, or neutrality in the source texts, is a crucial task. Multilingual sentiment analysis techniques were developed to analyze data in several languages; a notable deficiency of resources in multilingual sentiment analysis is one of the primary issues. Furthermore, the developed methods for multilingual sentiment analysis have some limitations such as data dependency, reliability, robustness, and computational complexity. To tackle these shortcomings, this research proposed a multilingual improved multi-attention Deep Learning model (M2PSC-DL), which leverages the advantages of the Bi-directional Long Short Term Memory (BiLSTM) classifier with improved attention mechanisms. The Multi-metric graph embedding technique encodes the data to provide more contextual information representation. Additionally, the combination of improved Positional Spatial Channel (SPC) attention increases the capability of the model to extract relevant features in the training process which leads to getting accurate results in sentiment analysis tasks. Furthermore, the research proposed an improved sigmoid activation for solving the vanishing gradient issues that help the model avoid gradient saturations. The validation results demonstrate that the M2PSC-DL model attains 96.26% accuracy, 96.06% precision, and 96.18% recall for the XED dataset which is far better than the traditional methods.<\/jats:p>","DOI":"10.3233\/idt-240773","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T15:32:49Z","timestamp":1725377569000},"page":"1915-1931","source":"Crossref","is-referenced-by-count":1,"title":["M2PSC: Multilingual sentiment analysis using improved multi-attention based Deep Learning model"],"prefix":"10.1177","volume":"18","author":[{"given":"Shruti","family":"Mathur","sequence":"first","affiliation":[]},{"given":"Gourav","family":"Shrivastava","sequence":"additional","affiliation":[]}],"member":"179","reference":[{"key":"10.3233\/IDT-240773_ref1","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.knosys.2016.08.012","article-title":"Sentiment and emotion classification over noisy labels","volume":"111","author":"Wang","year":"2016","journal-title":"Knowledge-Based Systems."},{"issue":"1","key":"10.3233\/IDT-240773_ref2","first-page":"37","article-title":"Sentimental analysis from imbalanced code-mixed data using machine learning approaches","volume":"41","author":"Srinivasan","year":"2023","journal-title":"Distributed and Parallel Databases."},{"issue":"3","key":"10.3233\/IDT-240773_ref3","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.1007\/s40747-021-00487-7","article-title":"Hatred and trolling detection transliteration framework using hierarchical LSTM in code-mixed social media text","volume":"9","author":"Shekhar","year":"2023","journal-title":"Complex & Intelligent Systems"},{"issue":"3","key":"10.3233\/IDT-240773_ref5","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1111\/j.1467-971X.1989.tb00678.x","article-title":"Code switching and code mixing as a communicative strategy in multilingual discourse","volume":"8","author":"Tay","year":"1989","journal-title":"World Englishes."},{"key":"10.3233\/IDT-240773_ref10","doi-asserted-by":"crossref","first-page":"100042","DOI":"10.1016\/j.nlp.2023.100042","article-title":"Language augmentation approach for code-mixed text classification","volume":"5","author":"Takawane","year":"2023","journal-title":"Natural Language Processing Journal."},{"key":"10.3233\/IDT-240773_ref12","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1561\/1500000011","article-title":"Opinion mining and sentiment analysis","volume":"2","author":"Pang","year":"2008","journal-title":"Found. Trends Inf. Retr."},{"key":"10.3233\/IDT-240773_ref14","doi-asserted-by":"publisher","first-page":"133961","DOI":"10.1109\/ACCESS.2021.3116053","article-title":"A multi-layer network for aspect-based cross-lingual sentiment classification","volume":"9","author":"Sattar","year":"2021","journal-title":"in IEEE Access."},{"key":"10.3233\/IDT-240773_ref16","doi-asserted-by":"publisher","first-page":"4175","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Machine Learning."},{"issue":"4","key":"10.3233\/IDT-240773_ref18","first-page":"1093","article-title":"Sentiment analysis algorithms and applications: A survey","volume":"5","author":"Medhat","year":"2014","journal-title":"in Shams Engineering Journal."},{"key":"10.3233\/IDT-240773_ref22","doi-asserted-by":"crossref","first-page":"37014","DOI":"10.1109\/ACCESS.2020.2973711","article-title":"A sentiment analysis method of capsule network based on BiLSTM","volume":"8","author":"Dong","year":"2020","journal-title":"IEEE Access."},{"key":"10.3233\/IDT-240773_ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2021\/9986920","article-title":"Hybrid deep learning models for sentiment analysis","volume":"2021","author":"Dang","year":"2021","journal-title":"Complexity."},{"issue":"1","key":"10.3233\/IDT-240773_ref24","doi-asserted-by":"crossref","first-page":"100151","DOI":"10.1016\/j.jjimei.2022.100151","article-title":"Offensive language identification in Dravidian languages using MPNet and CNN","volume":"3","author":"Chakravarthi","year":"2023","journal-title":"International Journal of Information Management Data Insights."},{"issue":"5","key":"10.3233\/IDT-240773_ref29","doi-asserted-by":"crossref","first-page":"e0232525","DOI":"10.1371\/journal.pone.0232525","article-title":"The influence of preprocessing on text classification using a bag-of-words representation","volume":"15","author":"HaCohen-Kerner","year":"2020","journal-title":"PloS One"},{"key":"10.3233\/IDT-240773_ref32","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.1109\/ACCESS.2017.2672677","article-title":"Comparison research on text pre-processing methods on Twitter sentiment analysis","volume":"5","author":"Jianqiang","year":"2017","journal-title":"IEEE Access."},{"key":"10.3233\/IDT-240773_ref33","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.procs.2019.05.008","article-title":"The impact of feature extraction on sentiment analysis","volume":"152","author":"Ahuja","year":"2019","journal-title":"Procedia Computer Science."},{"issue":"3","key":"10.3233\/IDT-240773_ref34","first-page":"503","article-title":"Convolutional neural network-based sentiment analysis with tf-idf based vectorization","volume":"11","author":"Kabra","year":"2023","journal-title":"Journal of Integrated Science and Technology."},{"key":"10.3233\/IDT-240773_ref41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0233-0","article-title":"Evaluation of maxout activations in deep learning across several big data domains","volume":"6","author":"Castaneda","year":"2019","journal-title":"Journal of Big Data."},{"issue":"5","key":"10.3233\/IDT-240773_ref42","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1109\/LGRS.2020.2988294","article-title":"SCAttNet: Semantic segmentation network with spatial and channel attention mechanism for high-resolution remote sensing images","volume":"18","author":"Li","year":"2020","journal-title":"IEEE Geoscience and Remote Sensing Letters."},{"key":"10.3233\/IDT-240773_ref44","doi-asserted-by":"crossref","first-page":"167240","DOI":"10.1109\/ACCESS.2019.2952888","article-title":"Aspect-based sentiment analysis with feature enhanced attention CNN-BiLSTM","volume":"7","author":"Meng","year":"2019","journal-title":"IEEE Access."}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDT-240773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T08:07:54Z","timestamp":1741680474000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDT-240773"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":19,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/idt-240773","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"type":"print","value":"1872-4981"},{"type":"electronic","value":"1875-8843"}],"subject":[],"published":{"date-parts":[[2024,9,16]]}}}